claude-workflow-v2
Universal Claude Code workflow plugin with agents, skills, hooks, and commands
The claude-workflow-v2 plugin is a universal workflow enhancement for Claude Code that bundles 7 specialized sub-agents, 26 slash commands, 14 knowledge skills, and 14 automation hooks into a single package. Developed by CloudAI-X, it automates common development tasks like generating commit messages, running multi-agent code reviews, security scanning, and systematic debugging. The plugin works natively in Claude Code and also supports skills.sh for cross-compatibility with Cursor, Codex, Windsurf, Cline, and 35+ other AI coding assistants. Developers install it to streamline Git workflows, enforce quality gates, and leverage specialized agents that activate automatically based on context.
Key Features
Use Cases
- 01Automatically generate conventional commit messages and execute full commit-push-PR workflows with a single slash command
- 02Run adversarial multi-agent verification before deployment to catch build failures, test regressions, lint violations, and security vulnerabilities
- 03Debug production issues systematically by triggering the debugger agent, which investigates errors, memory leaks, and race conditions
- 04Conduct thorough code reviews using the code-reviewer agent that analyzes logic correctness, identifies missing null checks, and suggests rate limiting
- 05Bootstrap understanding of new repositories with parallel 10-agent exploration that maps architecture, dependencies, and conventions
- 06Enforce security best practices through pre-commit hooks that block secrets in code and auto-spawn the security-auditor for auth/encryption changes
Related Plugins
View moreandrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
claude-workflow-v2 — FAQ
What is claude-workflow-v2?+
claude-workflow-v2 is a comprehensive Claude Code plugin that packages 7 specialized AI sub-agents, 26 workflow commands, 14 knowledge skills, and 14 automation hooks into a single installable extension. It automates development workflows like code review, commit generation, debugging, and security scanning.
How do I install claude-workflow-v2 in Claude Code?+
For the full plugin experience with agents and hooks, run 'npx install-claude-workflow-v2@latest' in your terminal. For skills-only installation compatible with multiple AI coding agents, use 'npx skills add CloudAI-X/claude-workflow-v2'. You can also install per-session with 'claude --plugin-dir ./claude-workflow-v2' after cloning the repository.
Which AI clients and agents work with this plugin?+
The complete plugin (agents, commands, hooks) works exclusively with Claude Code v1.0.33 or later. The 14 knowledge skills are compatible with 38+ AI coding agents including Cursor, Codex, Windsurf, Cline, and others when installed via skills.sh.
Does claude-workflow-v2 require API keys or special prerequisites?+
The plugin requires Claude Code v1.0.33+, Python 3 for hook scripts, and Git for version control features. Node.js is optional for npm-based commands. No additional API keys are needed for core functionality, though optional MCP server integrations (Slack, GitHub, Sentry) require their own credentials.
Is claude-workflow-v2 free to use?+
Yes, claude-workflow-v2 is open-source software released under the MIT license, making it free for both personal and commercial use.
How do the specialized agents activate automatically?+
Agents trigger based on keywords and context in your prompts: the debugger activates on error keywords, the security-auditor spawns for auth/JWT mentions, the orchestrator handles complex multi-step tasks, and the code-reviewer activates when you request reviews. Each agent's markdown definition specifies its auto-trigger conditions.
How do I install claude-workflow-v2?+
Open the source repository on GitHub and follow its README. claude-workflow-v2 is a plugin — MCP Agents Market links you directly to the official repo.
Is claude-workflow-v2 free?+
claude-workflow-v2 is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.